Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions starting with "Is that" or "Is it"

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements that inquire about the validity or nature of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mares
    -0.72
    bies
    -0.70
    CTV
    -0.67
    aband
    -0.67
    phia
    -0.66
    banks
    -0.65
    roups
    -0.63
    tails
    -0.62
    ipeg
    -0.61
    ãģ®ç
    -0.61
    POSITIVE LOGITS
     spoiler
    0.75
     really
    0.71
     kidding
    0.69
     Really
    0.67
    orio
    0.63
     Ready
    0.61
     sexist
    0.61
     presum
    0.61
     worth
    0.60
     ironic
    0.60
    Act Density 0.092%

    No Known Activations